Detects AI generation traces in articles (template phrases, piled-up transition words, repetitive sentence patterns, etc.), provides a risk score and revision suggestions, and can output a humanized polished version. Detection logic based on WeChat Official Account Platform Operation Norms Clause 3.27 (non-human automated creation behavior).
When to Use
- The user is preparing to publish an AI-assisted writing article to a WeChat Official Account
- The user wants to check whether an article has obvious AI traces
- The user wants to rewrite an AI-generated draft into a more natural human style
Workflow (MANDATORY)
You MUST follow these steps in order:
Step 1: Get the article
Determine the input source:
- If user provides a file path → read the file
- If user pastes text in the conversation → save to a temp file or use
--text
Step 2: Run analysis
python skills/lovstudio-anti-wechat-ai-check/scripts/analyze.py \
--input <path> --format json
Or with inline text:
python skills/lovstudio-anti-wechat-ai-check/scripts/analyze.py \
--text "文章内容" --format json
Step 3: Present findings
Show the user:
- Risk score (0-100) and risk level (LOW / MEDIUM / HIGH)
- Template phrases found — list each one with its location
- Structure issues — transition word density, paragraph uniformity, etc.
- Sentence issues — length uniformity, repeated starters, excessive "的"
Step 4: Ask the user
IMPORTANT: Use AskUserQuestion to ask what to do next:
| Option | Description |
|---|---|
| View report only | The user modifies it themselves; skill ends |
| Provide revision suggestions | List specific revision suggestions for each issue, without changing the original text |
| Directly output the revised version | Output the complete humanized polished article |
Step 5: Humanize (if requested)
When rewriting, follow these humanization rules:
5a. Eliminate template phrases
- Delete or replace each template phrase marked in the report
- "With the continuous development of technology" → directly state the specific thing ("After ChatGPT was released last year...")
- "In summary" → delete it, or replace it with a colloquial ending
5b. Reduce transition word density
- Target: transition word density < 15%
- Delete unnecessary "first/secondly/in addition/moreover"
- Replace generalized connectives with specific logical relationships
5c. Break sentence uniformity
- Deliberately create an alternation of long and short sentences: short sentences < 15 characters, long sentences > 40 characters
- Add colloquial expressions, rhetorical questions, exclamatory sentences
- Occasionally use incomplete sentences or elliptical sentences
5d. Break paragraph uniformity
- Some paragraphs have only one or two sentences, while some paragraphs can be very long
- Avoid every paragraph being the three-part pattern of "argument + evidence + summary"
5e. Add human touch
- Add personal experiences, specific cases, numerical details
- Use colloquial expressions ("put it plainly", "seriously", "think about it")
- Appropriately use non-standard but natural expressions
- Reduce use of the character "的" (target < 5%)
5f. Preserve the original meaning
- Core viewpoints and information must not be lost
- Keep technical terms; do not over-colloquialize
- Maintain the original text's stance and attitude
Step 6: Output
Output the humanized article as markdown. If the input was a file, also offer
to write the result back to a file (with -humanized suffix).
CLI Reference
| Argument | Default | Description |
|---|---|---|
--input, -i |
— | Input file path (.md, .txt) |
--text, -t |
— | Inline text to analyze |
--format, -f |
text |
Output format: text or json |
Dependencies
No external dependencies — stdlib only.